INDEX
Explanations
references to different nationalities and ethnic identities, particularly focusing on Indian and related terms
New Auto-Interp
Negative Logits
kasarigan
-0.88
Terrorism
-0.77
InputDecoration
-0.76
NOPQRST
-0.75
rungsseite
-0.74
للاسماء
-0.74
jScrollPane
-0.73
OMIT
-0.73
drums
-0.73
="@+
-0.71
POSITIVE LOGITS
Indian
1.15
Canadian
1.12
Mexican
1.10
American
1.09
Canadian
1.05
Brazilian
1.05
Indian
1.05
Egyptian
1.03
American
1.01
Vietnamese
1.01
Activations Density 0.208%